Computationally efficient fingerprint algorithm for automatic recognition

  • Authors:

  • M. A. Dabbah;W. L. Woo;S. S. Dlay

  • Affiliations:

  • School of Electrical, Electronic and Computer Engineering, University of Newcastle, Newcastle upon Tyne, United Kingdom;School of Electrical, Electronic and Computer Engineering, University of Newcastle, Newcastle upon Tyne, United Kingdom;School of Electrical, Electronic and Computer Engineering, University of Newcastle, Newcastle upon Tyne, United Kingdom

  • Venue:
  • SSIP'05 Proceedings of the 5th WSEAS international conference on Signal, speech and image processing
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a new computationally efficient fingerprint algorithm for automatic recognition (CEFAR). We use the Gabor filter to enhance the image before minutiae extraction within the sub-region in the fingerprint that was defined by the singularity point (SP). Accurate matching requires accurate extraction of minutiae and detection of SP. Conditional Number concept has been used after performing binarising and thinning operations in order to extract the minutiae from the enhanced fingerprint. For SP detection, core type was detected by using complex filtering applied to the orientation tensor field; this algorithm has been modified to reduce computational complexity. The matching methodology based on the star structure that is created using the minutiae and the SP. This structure is invariant with respect to global rotation and translation on the fingerprint due to the consistency of its formation. Comparing CEFAR to benchmark algorithms has shown that the CEFAR has maintained a high accuracy of EER less than 5%, together with dramatic reduction in the computation intensive requirements. There is a 60% reduction in SP detection and 41% of fingerprint image is only used for recognition, leading to a good efficiency.